Title :
A New Algorithm of Target Classification Based on Maximum and Minimum Polarizations
Author :
Yang, Wang ; Jiaguo, Lu ; Changyao, Zhang
Author_Institution :
Key Lab. of Intelligent Comput. & Signal Process. of Minist. of Educ., Anhui Univ., Hefei
Abstract :
The polarization signature of a given pixel in a radar image represents scattering mechanisms from various scattering elements. This paper presents an analysis of maximum and minimum polarizations of five kinds of polarization signatures: co-polarized, cross-polarized, completely polarized, completely unpolarized, and total available power signatures. We propose a new algorithm of target classification based on these maximum and minimum polarizations, then, conduct the experiment on the measured polarimetric SAR data. Experimental results show that this algorithm is robust to pixel-by-pixel target classification in radar images
Keywords :
electromagnetic wave polarisation; electromagnetic wave scattering; image classification; radar imaging; radar polarimetry; synthetic aperture radar; maximum polarization; measured polarimetric SAR data; minimum polarization; polarization signature; radar image; target classification; Classification algorithms; Polarization; Radar imaging; Radar polarimetry; Radar remote sensing; Radar scattering; Radar signal processing; Signal processing algorithms; Surface waves; Wavelength measurement; maximum and minimum polarizations; polarimetric SAR; polarization signatures; target decomposition;
Conference_Titel :
Radar, 2006. CIE '06. International Conference on
Conference_Location :
Shanghai
Print_ISBN :
0-7803-9582-4
Electronic_ISBN :
0-7803-9583-2
DOI :
10.1109/ICR.2006.343544
